Data mining in clinical trial text: transformers for classification and question answering tasks

Schmidt, Lena, Weeds, Julie and Higgins, Julian P T (2020) Data mining in clinical trial text: transformers for classification and question answering tasks. Health Informatics, Valletta, Malta, 24th-26th February 2020. Published in: Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies. 5 83-94. Science and Technology Publications ISSN 2184-4305 ISBN 9789897583988

[img] PDF - Accepted Version
Available under License Creative Commons Attribution-NonCommercial No Derivatives.

Download (2MB)

Abstract

This research on data extraction methods applies recent advances in natural language processing to evidence synthesis based on medical texts. Texts of interest include abstracts of clinical trials in English and in multilingual contexts. The main focus is on information characterized via the Population, Intervention, Comparator, and Outcome (PICO) framework, but data extraction is not limited to these fields. Recent neural network architectures based on transformers show capacities for transfer learning and increased performance on downstream natural language processing tasks such as universal reading comprehension, brought forward by this architecture’s use of contextualized word embeddings and self-attention mechanisms. This paper contributes to solving problems related to ambiguity in PICO sentence prediction tasks, as well as highlighting how annotations for training named entity recognition systems are used to train a high-performing, but nevertheless flexible architecture for question answering in systematic review automation. Additionally, it demonstrates how the problem of insufficient amounts of training annotations for PICO entity extraction is tackled by augmentation. All models in this paper were created with the aim to support systematic review (semi)automation. They achieve high F1 scores, and demonstrate the feasibility of applying transformer-based classification methods to support data mining in the biomedical literature.

Item Type: Conference Proceedings
Keywords: BERT, Data mining, Evidence-based Medicine, PICO Element Detection, Natural Language Processing, Question Answering, Sentence Classification, Systematic Review Automation, Transformer Neural Network
Schools and Departments: School of Engineering and Informatics > Informatics
Research Centres and Groups: Data Science Research Group
Subjects: Q Science > QA Mathematics > QA0075 Electronic computers. Computer science
Depositing User: Julie Weeds
Date Deposited: 06 Feb 2020 09:11
Last Modified: 07 Apr 2020 09:45
URI: http://sro.sussex.ac.uk/id/eprint/89770

View download statistics for this item

📧 Request an update